The repository provides code for running inference with the Meta Segment Anything Model 2 (SAM 2), links for downloading the trained model checkpoints, and example notebooks that show how to use th…

Official code implementation of General OCR Theory: Towards OCR-2.0 via a Unified End-to-end Model

Official implementation of the paper "Track the Answer: Extending TextVQA from Image to Video with Spatio-Temporal Clues"

[2024-NeurIPS] TextCtrl: Diffusion-based Scene Text Editing with Prior Guidance Control

Generate a transcript for your favourite Manga: Detect manga characters, text blocks and panels. Order panels. Cluster characters. Match texts to their speakers. Perform OCR.

Official Implementation of OCR-free Document Understanding Transformer (Donut) and Synthetic Document Generator (SynthDoG), ECCV 2022

[ECCV 2024] Elysium: Exploring Object-level Perception in Videos via MLLM

The official repo for [CVPR'23] "DeepSolo: Let Transformer Decoder with Explicit Points Solo for Text Spotting" & [ArXiv'23] "DeepSolo++: Let Transformer Decoder with Explicit Points Solo for Multi…

PyTorch implementation of paper "ARTrack" and "ARTrackV2"

[NeurIPS'24] GoMatching: A Simple Baseline for Video Text Spotting via Long and Short Term Matching

(CVPR 2024) Bridging the Gap Between End-to-End and Two-Step Text Spotting.

[NeurIPS2021] BOVText: A Large-Scale, Multidimensional Multilingual Dataset for Video Text Spotting

✨✨ Scene-Text Grounding for Text-Based Video Question Answering (arxiv)

Qwen2-VL is the multimodal large language model series developed by Qwen team, Alibaba Cloud.

[IJCV 2024] TransDETR: End-to-end Video Text Spotting with Transformer